用於改進 OCR辨識效果的 C# 影像校正濾鏡：圖片轉文字前置處理

using IronOcr;

// Instantiate IronTesseract
IronTesseract ocrTesseract = new IronTesseract();

// Add image
using var imageInput = new OcrImageInput("sample.jpg");
// Apply sharpen filter
imageInput.Sharpen();

// Export filtered image
imageInput.SaveAsImages("sharpen.jpg");

Imports IronOcr

' Instantiate IronTesseract
Private ocrTesseract As New IronTesseract()

' Add image
Private imageInput = New OcrImageInput("sample.jpg")
' Apply sharpen filter
imageInput.Sharpen()

' Export filtered image
imageInput.SaveAsImages("sharpen.jpg")

using IronOcr;

// Create OCR input
var imageInput = new OcrImageInput("low-res-scan.jpg");

// Apply enhance resolution filter with default 225 DPI
imageInput.EnhanceResolution();

// Or specify a custom DPI
imageInput.EnhanceResolution(300);

// Combine with OCR reading
var ocr = new IronTesseract();
var result = ocr.Read(imageInput);
Console.WriteLine($"Extracted text: {result.Text}");

Imports IronOcr

' Create OCR input
Dim imageInput As New OcrImageInput("low-res-scan.jpg")

' Apply enhance resolution filter with default 225 DPI
imageInput.EnhanceResolution()

' Or specify a custom DPI
imageInput.EnhanceResolution(300)

' Combine with OCR reading
Dim ocr As New IronTesseract()
Dim result = ocr.Read(imageInput)
Console.WriteLine($"Extracted text: {result.Text}")

using IronOcr;

// Load noisy document
var imageInput = new OcrImageInput("noisy-scan.pdf");

// Apply denoise filter with default 2x2 morphology
imageInput.DeNoise();

// Apply stronger denoising with 3x3 morphology
imageInput.DeNoise(true);

// Combine with other filters for severely degraded images
imageInput.DeNoise()
         .Sharpen()
         .EnhanceResolution(300);

// Process with OCR
var ocr = new IronTesseract();
var result = ocr.Read(imageInput);

// Check confidence levels
foreach (var page in result.Pages)
{
    Console.WriteLine($"Page confidence: {page.Confidence}%");
}

Imports IronOcr

' Load noisy document
Dim imageInput As New OcrImageInput("noisy-scan.pdf")

' Apply denoise filter with default 2x2 morphology
imageInput.DeNoise()

' Apply stronger denoising with 3x3 morphology
imageInput.DeNoise(True)

' Combine with other filters for severely degraded images
imageInput.DeNoise() _
         .Sharpen() _
         .EnhanceResolution(300)

' Process with OCR
Dim ocr As New IronTesseract()
Dim result = ocr.Read(imageInput)

' Check confidence levels
For Each page In result.Pages
    Console.WriteLine($"Page confidence: {page.Confidence}%")
Next

using IronOcr;

// Create OCR engine
var ocrTesseract = new IronTesseract();

// Apply dilate filter
var imageInput = new OcrImageInput("thin-text.jpg");
imageInput.Dilate();

// For more aggressive dilation
imageInput.Dilate(true);

// Practical example for faded receipt processing
var receiptInput = new OcrImageInput("faded-receipt.jpg");
receiptInput.Dilate()
           .DeNoise()
           .EnhanceResolution(300);

// Configure for better receipt reading
ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.SingleBlock;
ocrTesseract.Configuration.ReadBarCodes = true;

// Perform OCR
var result = ocrTesseract.Read(receiptInput);

Imports IronOcr

' Create OCR engine
Dim ocrTesseract As New IronTesseract()

' Apply dilate filter
Dim imageInput As New OcrImageInput("thin-text.jpg")
imageInput.Dilate()

' For more aggressive dilation
imageInput.Dilate(True)

' Practical example for faded receipt processing
Dim receiptInput As New OcrImageInput("faded-receipt.jpg")
receiptInput.Dilate() _
           .DeNoise() _
           .EnhanceResolution(300)

' Configure for better receipt reading
ocrTesseract.Configuration.PageSegmentationMode = TesseractPageSegmentationMode.SingleBlock
ocrTesseract.Configuration.ReadBarCodes = True

' Perform OCR
Dim result = ocrTesseract.Read(receiptInput)

using IronOcr;

// Create OCR instance
var ocrTesseract = new IronTesseract();

// Load image with thick text
var imageInput = new OcrImageInput("thick-text.jpg");

// Apply erode filter
imageInput.Erode();

// Stronger erosion for heavily bleeding text
imageInput.Erode(true);

// Example: Processing a poor-quality photocopy
var photocopyInput = new OcrImageInput("thick-text-photocopy.pdf");

// Apply erosion followed by sharpening for best results
photocopyInput.Erode()
              .Sharpen()
              .EnhanceResolution(300);

// Configure OCR for better accuracy
ocrTesseract.Configuration.BlackListCharacters = "~`@#$%^&*()_+-={}[]|\\:\";<>?,./";
ocrTesseract.Configuration.WhiteListCharacters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789 ";

var ocrResult = ocrTesseract.Read(photocopyInput);

// Extract with confidence check
var highConfidenceText = ocrResult.Blocks
    .Where(b => b.Confidence > 90)
    .Select(b => b.Text);

Imports IronOcr

' Create OCR instance
Dim ocrTesseract As New IronTesseract()

' Load image with thick text
Dim imageInput As New OcrImageInput("thick-text.jpg")

' Apply erode filter
imageInput.Erode()

' Stronger erosion for heavily bleeding text
imageInput.Erode(True)

' Example: Processing a poor-quality photocopy
Dim photocopyInput As New OcrImageInput("thick-text-photocopy.pdf")

' Apply erosion followed by sharpening for best results
photocopyInput.Erode() _
              .Sharpen() _
              .EnhanceResolution(300)

' Configure OCR for better accuracy
ocrTesseract.Configuration.BlackListCharacters = "~`@#$%^&*()_+-={}[]|\:"";<>?,./"
ocrTesseract.Configuration.WhiteListCharacters = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789 "

Dim ocrResult = ocrTesseract.Read(photocopyInput)

' Extract with confidence check
Dim highConfidenceText = ocrResult.Blocks _
    .Where(Function(b) b.Confidence > 90) _
    .Select(Function(b) b.Text)

using IronOcr;

var ocr = new IronTesseract();
var ocrInput = new OcrInput();

// Load a PDF file
ocrInput.LoadPdf("invoice.pdf");

// Apply multiple filters for comprehensive improvement
ocrInput.ToGrayScale()
        .DeNoise()
        .Sharpen()
        .EnhanceResolution(300);

// Perform OCR
OcrResult result = ocr.Read(ocrInput);

// Save the result as a searchable PDF with filters applied
result.SaveAsSearchablePdf("outputFiltered.pdf", true);

// Or save without filters to preserve original appearance
result.SaveAsSearchablePdf("outputOriginal.pdf", false);

// Export to other formats
result.SaveAsTextFile("extracted-text.txt");
result.SaveAsHocrFile("output.html");

Imports IronOcr

Dim ocr As New IronTesseract()
Dim ocrInput As New OcrInput()

' Load a PDF file
ocrInput.LoadPdf("invoice.pdf")

' Apply multiple filters for comprehensive improvement
ocrInput.ToGrayScale() _
        .DeNoise() _
        .Sharpen() _
        .EnhanceResolution(300)

' Perform OCR
Dim result As OcrResult = ocr.Read(ocrInput)

' Save the result as a searchable PDF with filters applied
result.SaveAsSearchablePdf("outputFiltered.pdf", True)

' Or save without filters to preserve original appearance
result.SaveAsSearchablePdf("outputOriginal.pdf", False)

' Export to other formats
result.SaveAsTextFile("extracted-text.txt")
result.SaveAsHocrFile("output.html")